國立虎尾科技大學 |

Infant Breath Sound Classification and Recognition.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Infant Breath Sound Classification and Recognition./
作者:	Jiang, Chao.
面頁冊數:	1 online resource (59 pages)
附註:	Source: Masters Abstracts International, Volume: 57-04.
Contained By:	Masters Abstracts International57-04(E).
標題:	Electrical engineering. -
電子資源:	click for full text (PQDT)
ISBN:	9780355628654

Infant Breath Sound Classification and Recognition.
Jiang, Chao.

Infant Breath Sound Classification and Recognition. - 1 online resource (59 pages)

Source: Masters Abstracts International, Volume: 57-04.

Thesis (M.S.)--Northern Illinois University, 2017.

Includes bibliographical references

It is well known that infants' breath sounds can indicate their different healthy conditions. It is possible for experts to distinguish infants' breath sounds through training and experience. These different breath sounds have different features. In this thesis we modify signal recognition techniques which are widely used for speech signal processing to process breath sound signal. Then we find out the relationship between breath sounds and some common diseases. Different breath sound are detected by Short Time Energy (STE) method. Then four feature extraction methods which include Linear Predictive Coding (LPC), Linear Predictive Cepstral Coefficients (LPCC), Mel Frequency Cepstral Coefficients (MFCC) and Time-Varying LPC are used to extract the features of those breath sounds. Infant breath sound recognition is processed by three most popular signal classification methods: Nearest Neighbor (NN), Hidden Markov Model (HMM), and Artificial Neural Network (ANN). The simulation and experiment results show that the proposed recognition algorithm offer a feasible solution for classifying infant breath sound in order to help with the diagnose and monitor/screen infant healthy condition.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780355628654Subjects--Topical Terms:

596380
Electrical engineering.
Index Terms--Genre/Form:

554714
Electronic books.

Infant Breath Sound Classification and Recognition.
LDR:02412ntm a2200337Ki 4500 001 919608
005 20181129115239.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355628654
035 $a (MiAaPQ)AAI10639856
035 $a (MiAaPQ)niu:13045
035 $a AAI10639856
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Jiang, Chao. $3 1182349
245 1 0 $a Infant Breath Sound Classification and Recognition.
264 0 $c 2017
300 $a 1 online resource (59 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 57-04.
500 $a Includes supplementary digital materials.
500 $a Adviser: Lichuan Liu.
502 $a Thesis (M.S.)--Northern Illinois University, 2017.
504 $a Includes bibliographical references
520 $a It is well known that infants' breath sounds can indicate their different healthy conditions. It is possible for experts to distinguish infants' breath sounds through training and experience. These different breath sounds have different features. In this thesis we modify signal recognition techniques which are widely used for speech signal processing to process breath sound signal. Then we find out the relationship between breath sounds and some common diseases. Different breath sound are detected by Short Time Energy (STE) method. Then four feature extraction methods which include Linear Predictive Coding (LPC), Linear Predictive Cepstral Coefficients (LPCC), Mel Frequency Cepstral Coefficients (MFCC) and Time-Varying LPC are used to extract the features of those breath sounds. Infant breath sound recognition is processed by three most popular signal classification methods: Nearest Neighbor (NN), Hidden Markov Model (HMM), and Artificial Neural Network (ANN). The simulation and experiment results show that the proposed recognition algorithm offer a feasible solution for classifying infant breath sound in order to help with the diagnose and monitor/screen infant healthy condition.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Electrical engineering. $3 596380
655 7 $a Electronic books. $2 local $3 554714
690 $a 0544
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Northern Illinois University. $b Electrical Engineering. $3 1182942
773 0 $t Masters Abstracts International $g 57-04(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10639856 $z click for full text (PQDT)